UnSearch
Analysis
UnSearch is a coherent instruction-only web search skill with expected API-key and external-provider data flows, but users should protect the key and treat retrieved web content as untrusted.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
"scrape_content": true ... "scraped_content": { "text": "Full page content..." }The skill retrieves full web page content for agent use; that content may contain untrusted instructions or misleading text.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
All requests require header: `X-API-Key: $UNSEARCH_API_KEY`
The skill requires an UnSearch API key to authenticate requests; this is expected for the service but is still a credential.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
**Base URL:** `https://api.unsearch.dev/api/v1` ... `query`: "your search query" ... `urls`: ["https://example.com/article"]
Queries and URLs are sent to an external UnSearch API provider, which is central to the skill's purpose.
